Pursuing Intelligent Behavior in Cyber-Physical Systems by Lightweight Diagnosis

Intelligence in its decisions is a trait that people have grown to expect from a cyber-physical system, in particular that it makes the right choices at runtime, that is, those that allow it to fulfill its tasks, even in case of faults or unexpected interactions with its environment. Analyzing how to continuously achieve the currently desired (and possibly continuously changing) goals and adapting its behavior to reach these goals is undoubtedly a serious challenge. This becomes even more challenging if the atomic actions a system can implement become unreliable due to faulty components or some exogenous event out of its control. Herein, a solution for the presented challenge is proposed. In particular, it is shown how to adopt a lightweight diagnosis concept to cope with such situations. The approach is based on rules coupled with means for rule selection that is based on previous information regarding success or failure of rule executions. Furthermore, Java-based framework of the lightweight diagnosis concept is presented, and the results obtained from an experimental evaluation considering several application scenarios are discussed. At the end, a qualitative comparison with other related approaches that should help the readers decide which approach works best for them is presented. An interactive preprint version of the article can be found here: .